1 Setup

1.1 Set working directory

knitr::opts_chunk$set(warning = FALSE, message = FALSE)
    knitr::opts_knit$set(root.dir = normalizePath("../data")) 

1.2 Packages

pacman::p_load(psych, lme4, nlme, tidyverse, lmerTest, gridExtra, ggplot2,patidyverse,tidyr, nlme, lmerTest, ggplot2, ggthemes, dplyr, rio, na.omit, performance, olsrr, tidyr, psych, dplyr,rowSum ,scapeMCMC, MCMCglmm, agridat, mlmRev, car, jtools, ggridges, DescTools, stringr, scater, gridExtra, cowplot, writexl, dplyr, tidyverse, foreign, irr, magrittr, plyr)

1.3 Data

# Load data
data_fragestellung2 <- rio::import("N183_multipom_r_rready.sav")

# select variables and define categorical data as factors
df2 <- data_fragestellung2 %>%
  mutate(the_sex = as.factor(the_sex), 
         pat_sex = as.factor(pat_sex),
         pat_id = as.factor(pat_id),
         the_id = as.factor(the_id), 
         bedingung = as.factor(bedingung)) %>%
  select(BAI_t1, BAI_t2, BAI_t3, BAI_t4, BAI_t5, BAI_t6, 
         BSI_t1, BSI_t2, BSI_t3, BSI_t4, BSI_t5, BSI_t6,
         BDI_t1, BDI_t2, BDI_t3, BDI_t4, BDI_t5, BDI_t6,
         n_sessions, age_th, age_pat_startth, 
         pom_pre, pom_int1, pom_int2, pom_post, pom_fu1, pom_fu2, pat_id, the_id, pat_sex, the_sex, EFT_all, SR_all, DB_all, I_all, B_all, C_all, PC_all, PD_all, CF_all, PE_all)

2 Datenbeschreibung

2.1 Deskriptive Analysen

describe(df2)
##                 vars  n  mean    sd median trimmed   mad   min    max  range
## BAI_t1             1 61 15.16  8.47  14.00   14.80  7.41  0.00  40.00  40.00
## BAI_t2             2 56 11.14  8.27   8.50   10.35  6.67  0.00  34.00  34.00
## BAI_t3             3 51  9.51  7.48   8.00    8.63  5.93  0.00  34.00  34.00
## BAI_t4             4 58  6.60  7.25   5.00    5.35  4.45  0.00  33.00  33.00
## BAI_t5             5 50  7.72  8.73   5.00    6.15  5.93  0.00  40.00  40.00
## BAI_t6             6 43  5.65  6.25   4.00    4.46  4.45  0.00  26.00  26.00
## BSI_t1             7 61 47.74 22.91  52.00   48.00 28.17  4.00  86.00  82.00
## BSI_t2             8 56 33.34 21.15  31.50   31.30 22.98  1.00  91.00  90.00
## BSI_t3             9 51 29.41 17.61  27.00   28.32 19.27  1.00  86.00  85.00
## BSI_t4            10 58 23.72 20.87  17.50   21.29 18.53  1.00 101.00 100.00
## BSI_t5            11 50 23.26 19.93  19.50   20.45 19.27  0.00  93.00  93.00
## BSI_t6            12 44 19.20 14.41  18.50   17.92 14.08  1.00  63.00  62.00
## BDI_t1            13 61 20.49 10.71  19.00   20.08 13.34  1.00  43.00  42.00
## BDI_t2            14 56 14.07 10.07  13.00   13.20 11.86  0.00  38.00  38.00
## BDI_t3            15 51 12.04  7.85  11.00   11.24  7.41  0.00  34.00  34.00
## BDI_t4            16 58  8.86  7.83   6.50    8.08  7.41  0.00  35.00  35.00
## BDI_t5            17 50  8.44  7.96   8.00    7.25  7.41  0.00  38.00  38.00
## BDI_t6            18 44  6.89  6.73   5.50    6.14  7.41  0.00  26.00  26.00
## n_sessions        19 61 24.82  5.47  26.00   25.63  2.97  9.00  31.00  22.00
## age_th            20 60 33.18  6.23  32.00   32.25  2.97 23.00  51.00  28.00
## age_pat_startth   21 61 30.30 10.61  27.00   28.33  5.93 20.00  68.00  48.00
## pom_pre           22 61 73.28 33.56  77.33   74.07 43.98  5.00 126.33 121.33
## pom_int1          23 56 51.12 31.58  49.83   48.40 36.08  3.00 138.33 135.33
## pom_int2          24 51 44.62 25.88  40.00   43.00 28.66  1.00 127.33 126.33
## pom_post          25 58 34.79 29.68  25.83   31.48 25.70  1.00 145.00 144.00
## pom_fu1           26 50 34.27 29.84  27.50   30.08 26.93  0.00 144.33 144.33
## pom_fu2           27 43 27.67 21.00  26.67   25.79 23.23  1.00  77.67  76.67
## pat_id*           28 61 31.00 17.75  31.00   31.00 22.24  1.00  61.00  60.00
## the_id*           29 60 16.32  8.69  16.00   16.35 10.38  1.00  32.00  31.00
## pat_sex*          30 60  1.57  0.50   2.00    1.58  0.00  1.00   2.00   1.00
## the_sex*          31 61  1.77  0.42   2.00    1.84  0.00  1.00   2.00   1.00
## EFT_all           32 61  2.10  0.42   2.15    2.09  0.45  1.30   3.13   1.83
## SR_all            33 61  1.55  0.31   1.53    1.53  0.33  1.00   2.42   1.42
## DB_all            34 61  1.87  0.39   1.81    1.85  0.44  1.17   2.83   1.67
## I_all             35 61  1.68  0.56   1.58    1.62  0.62  1.00   3.50   2.50
## B_all             36 61  2.11  0.29   2.09    2.09  0.26  1.42   2.93   1.51
## C_all             37 61  2.32  0.34   2.29    2.30  0.31  1.73   3.15   1.42
## PC_all            38 61  4.24  0.43   4.15    4.24  0.55  3.39   5.00   1.61
## PD_all            39 61  1.38  0.24   1.33    1.35  0.20  1.07   2.22   1.16
## CF_all            40 61  4.57  0.26   4.58    4.58  0.29  4.00   5.00   1.00
## PE_all            41 61  2.06  0.44   2.07    2.03  0.51  1.33   3.14   1.80
##                  skew kurtosis   se
## BAI_t1           0.38    -0.05 1.08
## BAI_t2           0.86    -0.22 1.10
## BAI_t3           1.14     1.16 1.05
## BAI_t4           1.89     3.75 0.95
## BAI_t5           1.89     3.82 1.23
## BAI_t6           1.74     2.78 0.95
## BSI_t1          -0.11    -1.15 2.93
## BSI_t2           0.85     0.18 2.83
## BSI_t3           0.74     0.51 2.47
## BSI_t4           1.27     1.74 2.74
## BSI_t5           1.32     1.80 2.82
## BSI_t6           0.79     0.26 2.17
## BDI_t1           0.22    -0.90 1.37
## BDI_t2           0.59    -0.48 1.35
## BDI_t3           0.82     0.23 1.10
## BDI_t4           0.94     0.50 1.03
## BDI_t5           1.40     2.38 1.13
## BDI_t6           0.81    -0.21 1.01
## n_sessions      -1.34     1.04 0.70
## age_th           1.40     1.55 0.80
## age_pat_startth  1.72     2.57 1.36
## pom_pre         -0.16    -1.12 4.30
## pom_int1         0.72     0.03 4.22
## pom_int2         0.76     0.65 3.62
## pom_post         1.23     1.65 3.90
## pom_fu1          1.43     2.40 4.22
## pom_fu2          0.57    -0.59 3.20
## pat_id*          0.00    -1.26 2.27
## the_id*          0.02    -1.07 1.12
## pat_sex*        -0.26    -1.96 0.06
## the_sex*        -1.25    -0.43 0.05
## EFT_all          0.15    -0.81 0.05
## SR_all           0.50    -0.07 0.04
## DB_all           0.39    -0.63 0.05
## I_all            0.99     0.86 0.07
## B_all            0.64     0.68 0.04
## C_all            0.58    -0.23 0.04
## PC_all           0.07    -1.04 0.05
## PD_all           1.24     1.44 0.03
## CF_all          -0.14    -1.08 0.03
## PE_all           0.45    -0.58 0.06
describeBy(df2, group = df2$pat_sex)
## 
##  Descriptive statistics by group 
## group: 1
##                 vars  n  mean    sd median trimmed   mad   min    max  range
## BAI_t1             1 26 15.46  6.72  16.50   15.36  5.19  2.00  32.00  30.00
## BAI_t2             2 24  9.96  7.18   7.50    9.40  7.41  1.00  26.00  25.00
## BAI_t3             3 21  7.90  6.48   6.00    7.24  4.45  0.00  24.00  24.00
## BAI_t4             4 23  5.30  6.42   4.00    4.11  5.93  0.00  27.00  27.00
## BAI_t5             5 18  6.89  7.31   3.00    6.31  4.45  0.00  23.00  23.00
## BAI_t6             6 15  2.80  3.14   2.00    2.46  2.97  0.00  10.00  10.00
## BSI_t1             7 26 47.42 23.44  51.50   47.36 29.65 12.00  84.00  72.00
## BSI_t2             8 24 30.21 17.57  30.50   28.80 20.76  5.00  70.00  65.00
## BSI_t3             9 21 25.57 16.54  24.00   23.82 14.83  4.00  67.00  63.00
## BSI_t4            10 23 21.96 23.62  15.00   18.00 14.83  1.00 101.00 100.00
## BSI_t5            11 18 24.06 19.60  20.00   22.25 20.02  2.00  75.00  73.00
## BSI_t6            12 16 13.06 10.27  10.50   12.71 11.86  1.00  30.00  29.00
## BDI_t1            13 26 20.04 11.24  18.50   19.23 14.08  6.00  43.00  37.00
## BDI_t2            14 24 11.79  9.01  11.50   11.00  8.90  0.00  38.00  38.00
## BDI_t3            15 21 10.86  7.66   8.00   10.12  5.93  0.00  34.00  34.00
## BDI_t4            16 23  7.52  8.58   5.00    6.05  5.93  0.00  35.00  35.00
## BDI_t5            17 18  8.06  7.16   7.50    7.44  7.41  0.00  26.00  26.00
## BDI_t6            18 16  4.50  5.22   2.00    4.14  2.97  0.00  14.00  14.00
## n_sessions        19 26 25.38  3.81  25.50   25.77  3.71 14.00  31.00  17.00
## age_th            20 26 33.77  5.84  32.00   33.14  2.97 26.00  51.00  25.00
## age_pat_startth   21 26 33.35 12.52  29.50   31.86  8.15 20.00  68.00  48.00
## pom_pre           22 26 72.62 34.07  77.17   72.26 46.70 21.00 126.33 105.33
## pom_int1          23 24 45.32 26.65  43.83   43.78 28.66  6.67 101.67  95.00
## pom_int2          24 21 39.06 24.91  37.67   36.25 21.74  4.00 107.00 103.00
## pom_post          25 23 31.25 33.57  19.33   25.58 20.26  1.00 145.00 144.00
## pom_fu1           26 18 34.41 28.19  28.17   31.77 31.63  3.00 108.00 105.00
## pom_fu2           27 15 17.07 14.49  12.00   16.18 14.83  2.00  43.67  41.67
## pat_id*           28 26 27.12 17.93  24.50   26.77 22.24  1.00  58.00  57.00
## the_id*           29 26 16.38  9.87  17.50   16.41 13.34  1.00  32.00  31.00
## pat_sex*          30 26  1.00  0.00   1.00    1.00  0.00  1.00   1.00   0.00
## the_sex*          31 26  1.62  0.50   2.00    1.64  0.00  1.00   2.00   1.00
## EFT_all           32 26  2.06  0.44   2.11    2.07  0.60  1.30   2.64   1.33
## SR_all            33 26  1.50  0.27   1.48    1.49  0.28  1.04   2.12   1.08
## DB_all            34 26  1.76  0.35   1.74    1.75  0.37  1.17   2.44   1.28
## I_all             35 26  1.64  0.59   1.47    1.57  0.56  1.00   3.50   2.50
## B_all             36 26  2.06  0.22   2.06    2.05  0.26  1.78   2.58   0.80
## C_all             37 26  2.28  0.32   2.23    2.25  0.25  1.77   3.06   1.29
## PC_all            38 26  4.28  0.42   4.26    4.29  0.47  3.44   5.00   1.56
## PD_all            39 26  1.37  0.22   1.33    1.36  0.20  1.07   1.80   0.73
## CF_all            40 26  4.49  0.26   4.46    4.49  0.29  4.00   4.92   0.92
## PE_all            41 26  2.04  0.45   1.98    2.03  0.54  1.33   2.89   1.56
##                  skew kurtosis   se
## BAI_t1           0.10     0.10 1.32
## BAI_t2           0.61    -0.88 1.47
## BAI_t3           0.91    -0.10 1.41
## BAI_t4           1.81     3.33 1.34
## BAI_t5           0.99    -0.46 1.72
## BAI_t6           0.94    -0.36 0.81
## BSI_t1          -0.09    -1.51 4.60
## BSI_t2           0.58    -0.59 3.59
## BSI_t3           0.89    -0.10 3.61
## BSI_t4           1.78     3.03 4.93
## BSI_t5           0.89     0.09 4.62
## BSI_t6           0.33    -1.61 2.57
## BDI_t1           0.48    -0.99 2.20
## BDI_t2           0.93     0.68 1.84
## BDI_t3           1.17     1.44 1.67
## BDI_t4           1.64     2.32 1.79
## BDI_t5           0.73    -0.14 1.69
## BDI_t6           0.65    -1.29 1.30
## n_sessions      -1.22     1.58 0.75
## age_th           1.36     1.41 1.15
## age_pat_startth  1.18     0.42 2.46
## pom_pre         -0.02    -1.44 6.68
## pom_int1         0.46    -0.94 5.44
## pom_int2         1.01     0.47 5.44
## pom_post         1.83     3.28 7.00
## pom_fu1          0.83     0.07 6.65
## pom_fu2          0.51    -1.38 3.74
## pat_id*          0.20    -1.41 3.52
## the_id*          0.04    -1.37 1.94
## pat_sex*          NaN      NaN 0.00
## the_sex*        -0.45    -1.87 0.10
## EFT_all         -0.11    -1.67 0.09
## SR_all           0.42    -0.48 0.05
## DB_all           0.33    -0.82 0.07
## I_all            1.20     1.51 0.12
## B_all            0.42    -0.80 0.04
## C_all            0.72    -0.04 0.06
## PC_all          -0.01    -1.05 0.08
## PD_all           0.39    -0.97 0.04
## CF_all           0.19    -1.12 0.05
## PE_all           0.22    -1.37 0.09
## ------------------------------------------------------------ 
## group: 2
##                 vars  n  mean    sd median trimmed   mad   min    max  range
## BAI_t1             1 34 15.24  9.64  13.00   14.79 12.60  0.00  40.00  40.00
## BAI_t2             2 31 12.29  9.03   9.00   11.40  7.41  0.00  34.00  34.00
## BAI_t3             3 29 10.86  8.07   9.00   10.08  7.41  0.00  34.00  34.00
## BAI_t4             4 34  7.50  7.83   5.50    6.18  5.19  0.00  33.00  33.00
## BAI_t5             5 31  8.35  9.63   6.00    6.48  5.93  0.00  40.00  40.00
## BAI_t6             6 27  7.19  7.11   5.00    6.22  4.45  0.00  26.00  26.00
## BSI_t1             7 34 48.79 22.67  52.50   49.43 26.69  4.00  86.00  82.00
## BSI_t2             8 31 35.94 23.83  33.00   33.68 25.20  1.00  91.00  90.00
## BSI_t3             9 29 32.41 18.34  29.00   31.64 20.76  1.00  86.00  85.00
## BSI_t4            10 34 24.71 19.38  21.50   23.29 23.72  1.00  77.00  76.00
## BSI_t5            11 31 23.19 20.64  20.00   20.20 20.76  0.00  93.00  93.00
## BSI_t6            12 27 21.89 15.05  23.00   20.96 14.83  1.00  63.00  62.00
## BDI_t1            13 34 21.06 10.53  22.00   21.14 11.86  1.00  42.00  41.00
## BDI_t2            14 31 15.58 10.73  14.00   14.96 13.34  0.00  36.00  36.00
## BDI_t3            15 29 12.79  8.13  11.00   12.32  8.90  0.00  30.00  30.00
## BDI_t4            16 34  9.68  7.38   9.50    9.32  8.90  0.00  24.00  24.00
## BDI_t5            17 31  8.90  8.51   8.00    7.48  7.41  0.00  38.00  38.00
## BDI_t6            18 27  7.78  6.87   6.00    7.22  7.41  0.00  26.00  26.00
## n_sessions        19 34 24.35  6.55  26.50   25.18  3.71  9.00  31.00  22.00
## age_th            20 33 32.82  6.64  31.00   31.89  2.97 23.00  51.00  28.00
## age_pat_startth   21 34 27.79  8.44  25.00   26.25  4.45 20.00  62.00  42.00
## pom_pre           22 34 74.93 33.47  77.50   76.83 42.01  5.00 123.67 118.67
## pom_int1          23 31 55.61 35.15  51.33   52.29 38.55  3.00 138.33 135.33
## pom_int2          24 29 48.83 26.65  44.33   47.92 26.19  1.00 127.33 126.33
## pom_post          25 34 36.88 27.46  31.33   35.02 30.64  1.00 104.33 103.33
## pom_fu1           26 31 34.88 31.44  27.67   30.11 23.72  0.00 144.33 144.33
## pom_fu2           27 27 32.06 21.23  33.33   31.06 19.27  1.00  77.67  76.67
## pat_id*           28 34 33.88 17.57  32.50   34.29 22.24  3.00  61.00  58.00
## the_id*           29 33 16.27  7.94  16.00   16.30  7.41  2.00  30.00  28.00
## pat_sex*          30 34  2.00  0.00   2.00    2.00  0.00  2.00   2.00   0.00
## the_sex*          31 34  1.88  0.33   2.00    1.96  0.00  1.00   2.00   1.00
## EFT_all           32 34  2.12  0.42   2.11    2.10  0.34  1.39   3.13   1.74
## SR_all            33 34  1.58  0.35   1.54    1.57  0.37  1.00   2.42   1.42
## DB_all            34 34  1.96  0.41   1.86    1.95  0.45  1.28   2.83   1.56
## I_all             35 34  1.72  0.55   1.65    1.68  0.51  1.00   3.25   2.25
## B_all             36 34  2.16  0.34   2.17    2.14  0.29  1.42   2.93   1.51
## C_all             37 34  2.36  0.36   2.32    2.35  0.36  1.73   3.15   1.42
## PC_all            38 34  4.20  0.44   4.11    4.19  0.58  3.39   5.00   1.61
## PD_all            39 34  1.38  0.27   1.28    1.34  0.12  1.13   2.22   1.09
## CF_all            40 34  4.64  0.24   4.68    4.66  0.27  4.17   5.00   0.83
## PE_all            41 34  2.06  0.43   2.07    2.02  0.42  1.33   3.14   1.80
##                  skew kurtosis   se
## BAI_t1           0.42    -0.46 1.65
## BAI_t2           0.78    -0.56 1.62
## BAI_t3           1.06     0.83 1.50
## BAI_t4           1.76     3.03 1.34
## BAI_t5           1.91     3.49 1.73
## BAI_t6           1.36     0.95 1.37
## BSI_t1          -0.17    -0.88 3.89
## BSI_t2           0.74    -0.33 4.28
## BSI_t3           0.56     0.57 3.41
## BSI_t4           0.64    -0.51 3.32
## BSI_t5           1.43     2.21 3.71
## BSI_t6           0.71     0.10 2.90
## BDI_t1          -0.06    -0.91 1.81
## BDI_t2           0.37    -1.00 1.93
## BDI_t3           0.58    -0.54 1.51
## BDI_t4           0.32    -1.15 1.27
## BDI_t5           1.51     2.51 1.53
## BDI_t6           0.73    -0.30 1.32
## n_sessions      -1.07    -0.16 1.12
## age_th           1.38     1.32 1.16
## age_pat_startth  2.27     5.90 1.45
## pom_pre         -0.32    -0.88 5.74
## pom_int1         0.63    -0.35 6.31
## pom_int2         0.55     0.63 4.95
## pom_post         0.53    -0.79 4.71
## pom_fu1          1.57     2.78 5.65
## pom_fu2          0.35    -0.77 4.09
## pat_id*         -0.13    -1.22 3.01
## the_id*         -0.03    -1.04 1.38
## pat_sex*          NaN      NaN 0.00
## the_sex*        -2.27     3.25 0.06
## EFT_all          0.47    -0.24 0.07
## SR_all           0.37    -0.39 0.06
## DB_all           0.26    -0.83 0.07
## I_all            0.75     0.07 0.09
## B_all            0.42     0.05 0.06
## C_all            0.40    -0.52 0.06
## PC_all           0.19    -1.11 0.08
## PD_all           1.49     1.65 0.05
## CF_all          -0.43    -0.85 0.04
## PE_all           0.71     0.06 0.07
describeBy(df2, group = df2$the_sex)
## 
##  Descriptive statistics by group 
## group: 1
##                 vars  n  mean    sd median trimmed   mad   min    max  range
## BAI_t1             1 14 14.00  7.03  16.50   14.17  4.45  2.00  24.00  22.00
## BAI_t2             2 14  9.14  7.68   6.50    8.42  5.19  1.00  26.00  25.00
## BAI_t3             3 11  7.55  4.87   9.00    7.00  2.97  2.00  18.00  16.00
## BAI_t4             4 13  5.08  4.82   5.00    4.45  4.45  0.00  17.00  17.00
## BAI_t5             5 10  6.00  6.78   3.00    4.88  1.48  0.00  21.00  21.00
## BAI_t6             6 10  3.90  3.25   2.50    3.62  2.97  0.00  10.00  10.00
## BSI_t1             7 14 47.86 28.36  37.00   47.67 34.10 12.00  86.00  74.00
## BSI_t2             8 14 28.14 19.41  22.00   26.58 17.79  5.00  70.00  65.00
## BSI_t3             9 11 25.82 18.22  26.00   23.56 17.79  5.00  67.00  62.00
## BSI_t4            10 13 24.69 18.50  21.00   23.64 17.79  1.00  60.00  59.00
## BSI_t5            11 10 25.30 24.20  15.50   22.25 19.27  0.00  75.00  75.00
## BSI_t6            12 10 13.80  8.78  14.50   13.50 11.86  2.00  28.00  26.00
## BDI_t1            13 14 20.43 12.32  18.50   19.58 14.08  8.00  43.00  35.00
## BDI_t2            14 14 11.93 10.48   9.50   10.75  7.41  0.00  38.00  38.00
## BDI_t3            15 11 10.64  8.50   7.00    8.67  1.48  5.00  34.00  29.00
## BDI_t4            16 13  9.38  7.11   7.00    9.00  4.45  0.00  23.00  23.00
## BDI_t5            17 10  8.10  8.69   7.00    6.88  9.64  0.00  26.00  26.00
## BDI_t6            18 10  3.60  4.86   1.50    2.75  2.22  0.00  14.00  14.00
## n_sessions        19 14 24.57  4.88  25.50   24.92  2.22 14.00  31.00  17.00
## age_th            20 14 34.14  6.19  33.00   33.67  3.71 23.00  51.00  28.00
## age_pat_startth   21 14 32.79 14.65  27.50   30.83  7.41 21.00  68.00  47.00
## pom_pre           22 14 72.95 41.36  61.67   72.92 56.83 21.00 125.33 104.33
## pom_int1          23 14 43.12 30.25  31.17   41.28 28.17  6.67 101.67  95.00
## pom_int2          24 11 38.97 27.47  37.67   34.30 21.74 13.00 107.00  94.00
## pom_post          25 13 35.77 26.16  31.00   34.48 23.72  1.00  84.67  83.67
## pom_fu1           26 10 35.40 34.87  23.33   30.75 29.65  0.00 108.00 108.00
## pom_fu2           27 10 18.70 13.82  17.00   17.67 15.32  2.00  43.67  41.67
## pat_id*           28 14 29.43 20.04  37.00   29.25 28.91  1.00  60.00  59.00
## the_id*           29 14 17.00  9.88  19.00   16.92 14.83  3.00  32.00  29.00
## pat_sex*          30 14  1.29  0.47   1.00    1.25  0.00  1.00   2.00   1.00
## the_sex*          31 14  1.00  0.00   1.00    1.00  0.00  1.00   1.00   0.00
## EFT_all           32 14  1.94  0.40   1.89    1.90  0.44  1.48   2.86   1.37
## SR_all            33 14  1.47  0.23   1.47    1.47  0.28  1.04   1.83   0.79
## DB_all            34 14  1.75  0.32   1.76    1.74  0.31  1.28   2.39   1.11
## I_all             35 14  1.71  0.50   1.65    1.67  0.56  1.17   2.75   1.58
## B_all             36 14  2.06  0.17   2.02    2.05  0.20  1.78   2.42   0.64
## C_all             37 14  2.28  0.32   2.26    2.27  0.25  1.77   2.94   1.17
## PC_all            38 14  4.07  0.51   3.96    4.05  0.44  3.39   5.00   1.61
## PD_all            39 14  1.42  0.34   1.28    1.39  0.17  1.07   2.22   1.16
## CF_all            40 14  4.51  0.27   4.46    4.50  0.31  4.17   5.00   0.83
## PE_all            41 14  1.92  0.39   1.84    1.88  0.33  1.44   2.86   1.42
##                  skew kurtosis    se
## BAI_t1          -0.51    -1.21  1.88
## BAI_t2           0.87    -0.63  2.05
## BAI_t3           0.54    -0.59  1.47
## BAI_t4           0.90     0.26  1.34
## BAI_t5           1.17    -0.20  2.14
## BAI_t6           0.59    -1.17  1.03
## BSI_t1           0.11    -1.89  7.58
## BSI_t2           0.70    -0.76  5.19
## BSI_t3           0.84    -0.23  5.49
## BSI_t4           0.56    -1.10  5.13
## BSI_t5           0.80    -0.80  7.65
## BSI_t6           0.14    -1.55  2.78
## BDI_t1           0.54    -1.14  3.29
## BDI_t2           1.06     0.25  2.80
## BDI_t3           1.83     2.25  2.56
## BDI_t4           0.42    -1.14  1.97
## BDI_t5           0.70    -0.80  2.75
## BDI_t6           1.03    -0.47  1.54
## n_sessions      -1.21     0.42  1.30
## age_th           1.04     1.78  1.65
## age_pat_startth  1.25     0.14  3.91
## pom_pre          0.10    -1.89 11.05
## pom_int1         0.56    -1.18  8.08
## pom_int2         1.21     0.65  8.28
## pom_post         0.57    -1.14  7.26
## pom_fu1          0.82    -0.72 11.03
## pom_fu2          0.44    -1.32  4.37
## pat_id*         -0.08    -1.69  5.36
## the_id*         -0.03    -1.51  2.64
## pat_sex*         0.85    -1.36  0.13
## the_sex*          NaN      NaN  0.00
## EFT_all          0.68    -0.46  0.11
## SR_all          -0.07    -1.11  0.06
## DB_all           0.28    -0.93  0.09
## I_all            0.71    -0.85  0.13
## B_all            0.30    -0.56  0.05
## C_all            0.39    -0.81  0.09
## PC_all           0.51    -1.09  0.14
## PD_all           1.23     0.25  0.09
## CF_all           0.36    -1.33  0.07
## PE_all           0.90     0.08  0.10
## ------------------------------------------------------------ 
## group: 2
##                 vars  n  mean    sd median trimmed   mad   min    max  range
## BAI_t1             1 47 15.51  8.89  13.00   15.10  8.90  0.00  40.00  40.00
## BAI_t2             2 42 11.81  8.43   9.00   11.00  6.67  0.00  34.00  34.00
## BAI_t3             3 40 10.05  8.02   8.00    9.12  6.67  0.00  34.00  34.00
## BAI_t4             4 45  7.04  7.80   5.00    5.62  4.45  0.00  33.00  33.00
## BAI_t5             5 40  8.15  9.18   6.00    6.47  6.67  0.00  40.00  40.00
## BAI_t6             6 33  6.18  6.86   4.00    4.93  4.45  0.00  26.00  26.00
## BSI_t1             7 47 47.70 21.39  52.00   48.13 23.72  4.00  86.00  82.00
## BSI_t2             8 42 35.07 21.65  32.00   32.94 22.98  1.00  91.00  90.00
## BSI_t3             9 40 30.40 17.54  27.00   29.59 19.27  1.00  86.00  85.00
## BSI_t4            10 45 23.44 21.70  16.00   20.70 16.31  1.00 101.00 100.00
## BSI_t5            11 40 22.75 19.04  20.00   20.25 18.53  1.00  93.00  92.00
## BSI_t6            12 34 20.79 15.43  22.00   19.71 17.79  1.00  63.00  62.00
## BDI_t1            13 47 20.51 10.33  20.00   20.46 11.86  1.00  42.00  41.00
## BDI_t2            14 42 14.79  9.96  14.00   14.06 11.86  0.00  36.00  36.00
## BDI_t3            15 40 12.43  7.73  11.50   11.91  8.15  0.00  30.00  30.00
## BDI_t4            16 45  8.71  8.09   6.00    7.81  7.41  0.00  35.00  35.00
## BDI_t5            17 40  8.53  7.89   8.50    7.28  6.67  0.00  38.00  38.00
## BDI_t6            18 34  7.85  6.95   7.00    7.21  8.15  0.00  26.00  26.00
## n_sessions        19 47 24.89  5.68  26.00   25.69  2.97  9.00  31.00  22.00
## age_th            20 46 32.89  6.28  31.00   32.00  2.97 25.00  51.00  26.00
## age_pat_startth   21 47 29.55  9.16  27.00   28.21  5.93 20.00  62.00  42.00
## pom_pre           22 47 73.38 31.40  77.33   74.50 36.08  5.00 126.33 121.33
## pom_int1          23 42 53.79 31.91  50.67   50.84 29.16  3.00 138.33 135.33
## pom_int2          24 40 46.17 25.57  41.67   45.36 26.69  1.00 127.33 126.33
## pom_post          25 45 34.50 30.89  24.33   30.60 27.18  1.00 145.00 144.00
## pom_fu1           26 40 33.99 28.94  30.33   30.25 27.92  1.00 144.33 143.33
## pom_fu2           27 33 30.39 22.18  32.67   28.94 30.64  1.00  77.67  76.67
## pat_id*           28 47 31.47 17.22  30.00   31.46 20.76  2.00  61.00  59.00
## the_id*           29 46 16.11  8.40  15.50   16.24  8.15  1.00  30.00  29.00
## pat_sex*          30 46  1.65  0.48   2.00    1.68  0.00  1.00   2.00   1.00
## the_sex*          31 47  2.00  0.00   2.00    2.00  0.00  2.00   2.00   0.00
## EFT_all           32 47  2.15  0.42   2.21    2.15  0.45  1.30   3.13   1.83
## SR_all            33 47  1.57  0.33   1.54    1.56  0.31  1.00   2.42   1.42
## DB_all            34 47  1.90  0.41   1.83    1.88  0.49  1.17   2.83   1.67
## I_all             35 47  1.67  0.59   1.58    1.60  0.62  1.00   3.50   2.50
## B_all             36 47  2.13  0.32   2.18    2.11  0.33  1.42   2.93   1.51
## C_all             37 47  2.33  0.35   2.31    2.31  0.34  1.73   3.15   1.42
## PC_all            38 47  4.29  0.39   4.30    4.29  0.39  3.67   5.00   1.33
## PD_all            39 47  1.37  0.21   1.33    1.35  0.20  1.07   1.87   0.80
## CF_all            40 47  4.59  0.25   4.67    4.61  0.31  4.00   5.00   1.00
## PE_all            41 47  2.10  0.45   2.11    2.08  0.55  1.33   3.14   1.80
##                  skew kurtosis   se
## BAI_t1           0.46    -0.19 1.30
## BAI_t2           0.81    -0.29 1.30
## BAI_t3           1.03     0.63 1.27
## BAI_t4           1.78     2.96 1.16
## BAI_t5           1.84     3.48 1.45
## BAI_t6           1.53     1.65 1.19
## BSI_t1          -0.26    -0.85 3.12
## BSI_t2           0.84     0.15 3.34
## BSI_t3           0.70     0.62 2.77
## BSI_t4           1.37     2.00 3.23
## BSI_t5           1.44     2.71 3.01
## BSI_t6           0.62    -0.21 2.65
## BDI_t1           0.05    -0.97 1.51
## BDI_t2           0.42    -0.71 1.54
## BDI_t3           0.45    -0.42 1.22
## BDI_t4           1.02     0.67 1.21
## BDI_t5           1.57     3.15 1.25
## BDI_t6           0.65    -0.48 1.19
## n_sessions      -1.34     0.98 0.83
## age_th           1.49     1.41 0.93
## age_pat_startth  1.59     2.41 1.34
## pom_pre         -0.31    -0.80 4.58
## pom_int1         0.74     0.14 4.92
## pom_int2         0.60     0.66 4.04
## pom_post         1.32     1.87 4.60
## pom_fu1          1.59     3.43 4.58
## pom_fu2          0.39    -0.89 3.86
## pat_id*          0.06    -1.21 2.51
## the_id*          0.02    -1.00 1.24
## pat_sex*        -0.62    -1.65 0.07
## the_sex*          NaN      NaN 0.00
## EFT_all         -0.02    -0.76 0.06
## SR_all           0.44    -0.33 0.05
## DB_all           0.32    -0.78 0.06
## I_all            1.03     0.99 0.09
## B_all            0.51     0.16 0.05
## C_all            0.60    -0.26 0.05
## PC_all           0.03    -1.11 0.06
## PD_all           0.67    -0.60 0.03
## CF_all          -0.30    -0.92 0.04
## PE_all           0.30    -0.70 0.06
describeBy(df2, group = data_fragestellung2$bedingung)
## 
##  Descriptive statistics by group 
## group: 1
##                 vars  n  mean    sd median trimmed   mad   min    max  range
## BAI_t1             1 28 14.54  8.30  13.00   13.67  6.67  3.00  40.00  37.00
## BAI_t2             2 26 11.23  7.21   9.00   10.64  5.93  1.00  29.00  28.00
## BAI_t3             3 23 10.13  7.29   9.00    9.53  7.41  0.00  34.00  34.00
## BAI_t4             4 26  6.38  5.43   5.00    5.95  5.93  0.00  18.00  18.00
## BAI_t5             5 22  7.45  9.14   4.50    5.83  5.19  0.00  40.00  40.00
## BAI_t6             6 22  4.23  3.91   4.00    3.89  5.93  0.00  13.00  13.00
## BSI_t1             7 28 43.25 21.42  43.00   42.71 22.98  5.00  86.00  81.00
## BSI_t2             8 26 35.23 22.44  31.50   33.64 23.72  5.00  90.00  85.00
## BSI_t3             9 23 30.83 19.88  27.00   28.68 13.34  1.00  86.00  85.00
## BSI_t4            10 26 25.85 21.17  18.00   24.23 21.50  1.00  77.00  76.00
## BSI_t5            11 22 22.59 21.20  17.50   19.39 17.05  1.00  93.00  92.00
## BSI_t6            12 22 18.50 13.43  19.50   17.56 15.57  1.00  45.00  44.00
## BDI_t1            13 28 19.96 11.01  18.50   19.67 11.86  1.00  43.00  42.00
## BDI_t2            14 26 15.46 10.03  14.50   14.95  8.90  0.00  38.00  38.00
## BDI_t3            15 23 13.26  9.08  11.00   12.53  7.41  0.00  34.00  34.00
## BDI_t4            16 26  9.65  8.05  10.00    9.36 10.38  0.00  23.00  23.00
## BDI_t5            17 22  8.64  9.12   7.00    7.06  8.90  0.00  38.00  38.00
## BDI_t6            18 22  8.18  6.66   8.50    7.83  8.90  0.00  21.00  21.00
## n_sessions        19 28 24.89  4.88  26.00   25.46  2.97 11.00  31.00  20.00
## age_th            20 28 34.36  5.72  33.00   33.75  4.45 26.00  51.00  25.00
## age_pat_startth   21 28 31.39 10.66  27.50   30.04  5.93 20.00  62.00  42.00
## pom_pre           22 28 68.06 32.54  66.17   67.61 43.00  7.33 125.33 118.00
## pom_int1          23 26 54.44 32.75  51.33   52.21 35.58  6.67 131.33 124.67
## pom_int2          24 23 47.46 29.67  39.33   44.12 22.73  1.00 127.33 126.33
## pom_post          25 26 37.63 29.95  30.17   35.79 34.59  1.00 104.33 103.33
## pom_fu1           26 22 33.71 32.37  25.17   29.20 25.45  1.00 144.33 143.33
## pom_fu2           27 22 28.09 20.20  30.00   27.09 23.97  1.00  68.33  67.33
## pat_id*           28 28 20.54 13.89  17.50   19.62 16.31  2.00  61.00  59.00
## the_id*           29 27 11.85  7.82  11.00   11.17  7.41  1.00  32.00  31.00
## pat_sex*          30 27  1.52  0.51   2.00    1.52  0.00  1.00   2.00   1.00
## the_sex*          31 28  1.79  0.42   2.00    1.83  0.00  1.00   2.00   1.00
## EFT_all           32 28  2.28  0.41   2.36    2.28  0.40  1.48   3.13   1.65
## SR_all            33 28  1.52  0.28   1.53    1.52  0.34  1.00   2.12   1.12
## DB_all            34 28  1.78  0.40   1.77    1.76  0.49  1.17   2.67   1.50
## I_all             35 28  1.58  0.43   1.57    1.57  0.43  1.00   2.42   1.42
## B_all             36 28  2.07  0.28   2.01    2.05  0.26  1.60   2.87   1.27
## C_all             37 28  2.28  0.33   2.26    2.25  0.24  1.77   3.15   1.38
## PC_all            38 28  4.24  0.40   4.15    4.24  0.36  3.44   5.00   1.56
## PD_all            39 28  1.41  0.26   1.33    1.38  0.20  1.07   2.22   1.16
## CF_all            40 28  4.56  0.29   4.48    4.57  0.38  4.00   4.94   0.95
## PE_all            41 28  2.25  0.44   2.22    2.25  0.42  1.39   3.14   1.75
##                  skew kurtosis   se
## BAI_t1           1.13     1.43 1.57
## BAI_t2           0.78    -0.34 1.41
## BAI_t3           1.26     2.56 1.52
## BAI_t4           0.65    -0.67 1.06
## BAI_t5           2.07     4.61 1.95
## BAI_t6           0.42    -0.98 0.83
## BSI_t1           0.19    -1.05 4.05
## BSI_t2           0.64    -0.46 4.40
## BSI_t3           1.07     0.65 4.14
## BSI_t4           0.58    -0.82 4.15
## BSI_t5           1.65     2.92 4.52
## BSI_t6           0.40    -1.02 2.86
## BDI_t1           0.38    -0.96 2.08
## BDI_t2           0.46    -0.48 1.97
## BDI_t3           0.76    -0.34 1.89
## BDI_t4           0.21    -1.47 1.58
## BDI_t5           1.62     2.61 1.94
## BDI_t6           0.23    -1.26 1.42
## n_sessions      -1.44     1.37 0.92
## age_th           1.23     0.91 1.08
## age_pat_startth  1.29     0.90 2.01
## pom_pre          0.11    -1.22 6.15
## pom_int1         0.54    -0.45 6.42
## pom_int2         1.00     0.51 6.19
## pom_post         0.45    -1.09 5.87
## pom_fu1          1.76     3.50 6.90
## pom_fu2          0.22    -1.17 4.31
## pat_id*          0.74     0.30 2.63
## the_id*          0.70     0.14 1.51
## pat_sex*        -0.07    -2.07 0.10
## the_sex*        -1.32    -0.27 0.08
## EFT_all         -0.07    -0.64 0.08
## SR_all           0.08    -0.80 0.05
## DB_all           0.49    -0.76 0.08
## I_all            0.30    -1.03 0.08
## B_all            0.85     0.26 0.05
## C_all            0.95     0.63 0.06
## PC_all           0.17    -0.67 0.08
## PD_all           1.37     1.59 0.05
## CF_all          -0.07    -1.40 0.05
## PE_all           0.12    -0.64 0.08
## ------------------------------------------------------------ 
## group: 2
##                 vars  n  mean    sd median trimmed   mad   min    max  range
## BAI_t1             1 33 15.70  8.70  17.00   15.81  7.41  0.00  32.00  32.00
## BAI_t2             2 30 11.07  9.21   7.50   10.04  8.15  0.00  34.00  34.00
## BAI_t3             3 28  9.00  7.73   6.00    8.29  4.45  0.00  29.00  29.00
## BAI_t4             4 32  6.78  8.53   4.50    4.85  5.19  0.00  33.00  33.00
## BAI_t5             5 28  7.93  8.56   5.00    6.75  5.93  0.00  37.00  37.00
## BAI_t6             6 21  7.14  7.84   3.00    5.76  2.97  0.00  26.00  26.00
## BSI_t1             7 33 51.55 23.77  56.00   52.63 26.69  4.00  86.00  82.00
## BSI_t2             8 30 31.70 20.21  31.50   29.33 20.76  1.00  91.00  90.00
## BSI_t3             9 28 28.25 15.78  27.50   28.29 22.24  4.00  53.00  49.00
## BSI_t4            10 32 22.00 20.80  17.50   18.96 15.57  1.00 101.00 100.00
## BSI_t5            11 28 23.79 19.26  21.00   21.88 17.79  0.00  75.00  75.00
## BSI_t6            12 22 19.91 15.61  18.50   18.28 13.34  1.00  63.00  62.00
## BDI_t1            13 33 20.94 10.60  21.00   20.63 11.86  1.00  42.00  41.00
## BDI_t2            14 30 12.87 10.12  11.00   11.88 11.86  0.00  36.00  36.00
## BDI_t3            15 28 11.04  6.68  10.50   10.75  7.41  0.00  28.00  28.00
## BDI_t4            16 32  8.22  7.71   6.00    7.12  5.93  0.00  35.00  35.00
## BDI_t5            17 28  8.29  7.10   8.50    7.54  7.41  0.00  26.00  26.00
## BDI_t6            18 22  5.59  6.70   3.00    4.56  4.45  0.00  26.00  26.00
## n_sessions        19 33 24.76  6.01  26.00   25.59  2.97  9.00  31.00  22.00
## age_th            20 32 32.16  6.56  30.00   31.04  2.97 23.00  51.00  28.00
## age_pat_startth   21 33 29.36 10.65  26.00   27.30  5.93 20.00  68.00  48.00
## pom_pre           22 33 77.72 34.27  80.00   79.65 44.97  5.00 126.33 121.33
## pom_int1          23 30 48.26 30.78  43.67   45.21 31.88  3.00 138.33 135.33
## pom_int2          24 28 42.29 22.59  42.50   42.17 29.40  4.00  82.67  78.67
## pom_post          25 32 32.48 29.74  22.33   28.03 21.00  2.00 145.00 143.00
## pom_fu1           26 28 34.71 28.29  33.17   31.65 31.38  0.00 108.00 108.00
## pom_fu2           27 21 27.24 22.29  25.00   24.69 22.24  1.67  77.67  76.00
## pat_id*           28 33 39.88 15.84  44.00   41.37 14.83  1.00  60.00  59.00
## the_id*           29 33 19.97  7.67  21.00   20.48  8.90  3.00  31.00  28.00
## pat_sex*          30 33  1.61  0.50   2.00    1.63  0.00  1.00   2.00   1.00
## the_sex*          31 33  1.76  0.44   2.00    1.81  0.00  1.00   2.00   1.00
## EFT_all           32 33  1.95  0.38   1.88    1.93  0.45  1.30   2.70   1.39
## SR_all            33 33  1.57  0.34   1.50    1.54  0.31  1.00   2.42   1.42
## DB_all            34 33  1.94  0.38   1.83    1.92  0.33  1.28   2.83   1.56
## I_all             35 33  1.76  0.65   1.58    1.69  0.62  1.00   3.50   2.50
## B_all             36 33  2.15  0.29   2.16    2.13  0.23  1.42   2.93   1.51
## C_all             37 33  2.36  0.35   2.33    2.35  0.37  1.73   3.15   1.42
## PC_all            38 33  4.24  0.46   4.30    4.24  0.61  3.39   5.00   1.61
## PD_all            39 33  1.35  0.23   1.27    1.33  0.20  1.07   2.07   1.00
## CF_all            40 33  4.58  0.24   4.67    4.59  0.25  4.17   5.00   0.83
## PE_all            41 33  1.89  0.36   1.74    1.87  0.22  1.33   2.67   1.33
##                  skew kurtosis   se
## BAI_t1          -0.20    -0.97 1.51
## BAI_t2           0.84    -0.48 1.68
## BAI_t3           1.04    -0.02 1.46
## BAI_t4           1.92     2.92 1.51
## BAI_t5           1.60     2.49 1.62
## BAI_t6           1.35     0.41 1.71
## BSI_t1          -0.39    -1.09 4.14
## BSI_t2           1.01     0.72 3.69
## BSI_t3          -0.01    -1.38 2.98
## BSI_t4           1.83     4.13 3.68
## BSI_t5           0.90     0.13 3.64
## BSI_t6           0.95     0.50 3.33
## BDI_t1           0.08    -0.94 1.85
## BDI_t2           0.70    -0.55 1.85
## BDI_t3           0.49    -0.51 1.26
## BDI_t4           1.56     2.61 1.36
## BDI_t5           0.78     0.01 1.34
## BDI_t6           1.41     1.47 1.43
## n_sessions      -1.21     0.52 1.05
## age_th           1.65     2.21 1.16
## age_pat_startth  2.04     4.00 1.85
## pom_pre         -0.40    -0.98 5.97
## pom_int1         0.85     0.38 5.62
## pom_int2         0.01    -1.25 4.27
## pom_post         1.84     4.12 5.26
## pom_fu1          0.94     0.27 5.35
## pom_fu2          0.81    -0.36 4.86
## pat_id*         -0.74    -0.55 2.76
## the_id*         -0.47    -0.83 1.34
## pat_sex*        -0.41    -1.88 0.09
## the_sex*        -1.15    -0.70 0.08
## EFT_all          0.28    -1.03 0.07
## SR_all           0.62    -0.16 0.06
## DB_all           0.37    -0.60 0.07
## I_all            0.90     0.11 0.11
## B_all            0.45     0.96 0.05
## C_all            0.28    -0.77 0.06
## PC_all           0.01    -1.37 0.08
## PD_all           1.01     0.61 0.04
## CF_all          -0.19    -0.89 0.04
## PE_all           0.61    -0.67 0.06
# Amount of Therapists
# df2 %>% filter(!is.na(the_id)) %>% dplyr::count(the_id,the_sex, sort = TRUE)

(9/32)*100 #-> 31.03 % male therapists
## [1] 28.125
(23/32)*100 #-> 68.97 % female therapists 
## [1] 71.875

2.2 Inter-Rater Reliabilität

# Data
df_icc <- read.spss("n33_3raterinnenICC.sav", to.data.frame = T)
df_icc$raterin<-as.factor(df_icc$raterin)
df_icc_items <- df_icc %>% dplyr::select(M1:M69)
item_names <- colnames(df_icc_items) 

# Loop for ICC calculations
df_icc_summary <- data.frame()  
for (x in item_names) { 
 z <-df_icc %>% dplyr::select(pat_id, raterin, t, x) %>% spread(raterin, x) %>% dplyr::select("1", "2", "3")
 z.icc <- icc(z, model = "twoway", type = "agreement", unit = "single")
    a <- data.frame(x, round(z.icc$value,3), z.icc$lbound, z.icc$ubound)
    names(a) <- c("Item", "ICC Value", "UG - KI", "OG - KI") 
    df_icc_summary <- rbind(df_icc_summary, a)  
}
# Tabellenvorberitung
df_icc_summary_rounded<-df_icc_summary %>% mutate_at(vars(-Item), funs(round(., 2)))
df_icc_summary_rounded_zero<-pmax(df_icc_summary_rounded,0)
df_icc_summary_rounded_zero[is.na(df_icc_summary_rounded_zero)] <- 0

# Tabelle abspeichern
df_icc_summary_rounded_zero
##    Item ICC Value UG - KI OG - KI
## 1    M1      0.74    0.57    0.86
## 2    M2      0.77    0.62    0.88
## 3    M3      0.87    0.77    0.93
## 4    M4      0.73    0.54    0.86
## 5    M5      0.47    0.24    0.68
## 6    M6      0.57    0.35    0.75
## 7    M7      0.33    0.10    0.57
## 8    M9      0.58    0.36    0.76
## 9   M10      0.00    0.00    0.00
## 10  M11      0.37    0.14    0.61
## 11  M12      0.38    0.14    0.61
## 12  M13      0.00    0.00    0.24
## 13  M15      0.94    0.89    0.97
## 14  M16      0.00    0.00    0.22
## 15  M17      0.72    0.55    0.85
## 16  M18      0.00    0.00    0.26
## 17  M20      0.31    0.08    0.55
## 18  M21      0.42    0.19    0.65
## 19  M22      0.32    0.09    0.56
## 20  M23      0.00    0.00    0.23
## 21  M24      0.11    0.00    0.38
## 22  M25      0.36    0.12    0.59
## 23  M27      0.36    0.13    0.59
## 24  M28      0.10    0.00    0.31
## 25  M29      0.42    0.19    0.65
## 26  M31      0.19    0.00    0.44
## 27  M33      0.51    0.28    0.71
## 28  M34      0.80    0.67    0.90
## 29  M35      0.56    0.34    0.75
## 30  M36      0.56    0.34    0.75
## 31  M37      0.12    0.00    0.37
## 32  M39      0.41    0.18    0.63
## 33  M40      0.26    0.04    0.51
## 34  M43      0.17    0.00    0.44
## 35  M44      0.58    0.37    0.76
## 36  M46      0.16    0.00    0.41
## 37  M47      0.84    0.72    0.92
## 38  M48      0.34    0.11    0.58
## 39  M49      0.55    0.33    0.74
## 40  M50      0.41    0.18    0.64
## 41  M51      0.39    0.16    0.62
## 42  M54      0.41    0.16    0.64
## 43  M56      0.23    0.00    0.49
## 44  M60      0.00    0.00    0.24
## 45  M61      0.57    0.36    0.75
## 46  M62      0.93    0.87    0.96
## 47  M63      0.10    0.00    0.34
## 48  M64      0.65    0.45    0.81
## 49  M65      0.29    0.07    0.53
## 50  M66      0.60    0.39    0.77
## 51  M67      0.52    0.30    0.72
## 52  M68      0.00    0.00    0.26
## 53  M69      0.00    0.00    0.00
write_xlsx(df_icc_summary_rounded_zero,"sumary_icc.xlsx")

2.3 Subskalen: Zeitlicher Verlauf

# Data
item_ausprägung <- read.spss("N183_Fragestellung_sub.sav", to.data.frame = T)
item_ausprägung$Subskala <- as.factor(item_ausprägung$Index1) 
item_ausprägung$Bedingung <- as.factor(item_ausprägung$bedingung)
item_ausprägung$Therapie_Drittel <- as.numeric(item_ausprägung$t)
item_ausprägung$Rating <- (item_ausprägung$item)
item_ausprägung$Subskala <- revalue(item_ausprägung$Subskala, c(
                            "PD "   ="Psychodynamic", 
                             "PE " = "Process-Experiential", 
                             "I  " = "Interpersonal", 
                             "PC " = "Person-Centered", 
                             "CF " = "Common Factors", 
                             "B  " = "Behavioral", 
                             "C  " = "Cognitive", 
                             "DB " = "Dialectic-Behavioral", 
                             "EFT" = "Emotion-Focused",
                             "SR " = "Sef-Regulation"))

# Plot
Abbildung_5<-ggplot(item_ausprägung) +
                        stat_summary(aes(x = Therapie_Drittel, y = Rating, group = paste0(Subskala,Bedingung), color = Subskala, linetype=Bedingung), fun=mean, geom="line")  + 
                        ylim(1,5) +
                        xlim(1,3)+
                        theme_classic()+
                        scale_x_continuous(breaks=c(1,2,3))+
                        scale_linetype_discrete(labels=c("1" = "+EFT", "2" = "+SR")) 

Abbildung_5

ggsave("Abbildung_5.jpg", plot = Abbildung_5, scale = 1,
  width = 15,
  height = 12,
  units = c("cm"),
  dpi = 500,)   

2.4 Items: Häufigkeit pro Therapeut*in

# Data
df_hm_orig <- read.spss("N183_Fragestellung1.sav", to.data.frame = T)
df_hm <- df_hm_orig %>% dplyr::select(the_id,t,PD:EFT)
df_hm$Therapeutin<-as.factor(df_hm$the_id)
df_hm_m <- df_hm %>%
  group_by(Therapeutin) %>%
  summarise_at(vars(PD:EFT), list(mean))
df_hm_m_long <- gather(df_hm_m, Subskala, Rating, PD:EFT, factor_key=TRUE)
df_hm_m_long <- na.omit(df_hm_m_long)
levels(df_hm_m_long$Therapeutin) <- 1:40

# Plot: Heatmap 
Heatmap_Subskala_Th <- ggplot(df_hm_m_long, aes(Subskala, Therapeutin, fill=Rating)) + 
                        geom_tile() +
                        scale_fill_continuous(limits = c(1, 5), breaks = seq(1, 5, by = 1)) +
                        guides(fill = guide_colourbar(barwidth = 0.5,
                                                      barheight = 15))+
                        scale_x_discrete("Subskala", labels = c(
                                                  "PD"  ="Psychodynamic", 
                                                   "PE" = "Process-Experiential", 
                                                   "I" = "Interpersonal", 
                                                   "PC" = "Person-Centered", 
                                                   "CF" = "Common Factors", 
                                                   "B" = "Behavioral", 
                                                   "C" = "Cognitive", 
                                                   "DB" = "Dialectic-Behavioral", 
                                                   "EFT" = "Emotion-Focused",
                                                   "SR" = "Sef-Regulation"))+
                       theme(axis.text.x = element_text(angle = 45, hjust = 1))
Heatmap_Subskala_Th

ggsave("Heatmap_Subskala_Th.jpg", plot = Heatmap_Subskala_Th, scale = 1,
  width = 12,
  height = 13,
  units = c("cm"),
  dpi = 500,)

2.5 Plot: Durchschnittliche Frequenz und Intensität der angewandten Subskalen pro Bedingung

# Data
data_r_analysen_ready <- data_fragestellung2
data_r_analysen_ready$condition <- as.factor(data_r_analysen_ready$bedingung)
data_r_analysen_ready_long <- gather(data_r_analysen_ready, Subskala, measurement, PD_all:EFT_all, factor_key=TRUE)

# Boxplot
Boxplot_Bedingungen_Subskalen <- ggplot(data_r_analysen_ready_long, aes(x=Subskala, y=measurement, fill=condition)) + 
  geom_boxplot() +
  theme_apa() +
  xlab("Theorie-(un)spezfisiche Interventionen") +
   scale_x_discrete(labels=c("PD_all" = "Psychodynamic", 
                             "PE_all" = "Process-Experiential", 
                             "I_all" = "Interpersonal", 
                             "PC_all" = "Person-Centered", 
                             "CF_all" = "Common Factors", 
                             "B_all" = "Behavioral", 
                             "C_all" = "Cognitive", 
                             "DB_all" = "Dialectic-Behavioral", 
                             "EFT_all" = "Emotion-Focused",
                             "SR_all" = "Sef-Regulation" 
                             )) +
  ylab("Rating") +
  scale_fill_discrete(name = "Bedingung", labels=c("1" = "+EFT",
                                                   "2" = "+SR")) +
 theme(axis.text.x = element_text(angle = 45, hjust = 1))
Boxplot_Bedingungen_Subskalen

ggsave("Subskala_Wirkfaktoren.jpg", plot = Boxplot_Bedingungen_Subskalen, scale = 1,
  width = 15,
  height = 10,
  units = c("cm"),
  dpi = 300,)

## Alternativ: Basic Violine Plot

Violineplot_Bedingungen_Subskalen <- ggplot(data_r_analysen_ready_long, aes(x=Subskala, y=measurement, fill=bedingung)) + 
  geom_violin(size=0.2) +
  theme_apa() +
  xlab("Theorie (un)-spezfisiche Interventionen") +
  scale_x_discrete(labels=c("PD_all" = "Psychodynamic", 
                            "PE_all" = "Process-Experiential", 
                            "I_all" = "Interpersonal", 
                            "PC_all" = "Person-Centered", 
                            "CF_all" = "Common Factors", 
                            "B_all" = "Behavioral", 
                            "C_all" = "Cognitive", 
                            "DB_all" = "Dialectic-Behavioural", 
                            "SR_all" = "Sef-Regulation", 
                            "EFT_all" = "Emotion-Focused")) +
  ylab("Rating") +
  scale_fill_discrete(name = "Bedingung", labels=c("1" = "+EFT",
                                                   "2" = "+SR")) +
  theme(axis.text.x = element_text(angle = 0))+
  coord_flip()
Violineplot_Bedingungen_Subskalen

3 Hierarchical Linear Modeling

3.1 Data

# Wide to Long
df2_long <- select(df2, BAI_t1, BAI_t2, BAI_t3, BAI_t4, BAI_t5, BAI_t6, 
                   BSI_t1, BSI_t2, BSI_t3, BSI_t4, BSI_t5, BSI_t6,
                   BDI_t1, BDI_t2, BDI_t3, BDI_t4, BDI_t5, BDI_t6,
                   n_sessions, age_th, age_pat_startth, pom_pre, pom_int1, pom_int2, pom_post, pom_fu1, pom_fu2, pat_id, the_id, pat_sex, the_sex, EFT_all, SR_all, DB_all, I_all, B_all, C_all, PC_all, PD_all, CF_all, PE_all)%>%
  gather("Time","Pomvalue", pom_pre: pom_fu2 ) %>% 
  mutate(Time = replace(Time,Time=="pom_pre", "0")) %>%
  mutate(Time = replace(Time,Time=="pom_int1", "1")) %>%
  mutate(Time = replace(Time,Time=="pom_int2", "2")) %>%
  mutate(Time = replace(Time,Time=="pom_post", "3")) %>%
  mutate(Time = replace(Time,Time=="pom_fu1", "4"))%>%
  mutate(Time = replace(Time,Time=="pom_fu2", "5"))%>%
  mutate(Time = as.numeric(Time))

3.2 Prüfung der Vorraussetzungen

3.2.1 Linearität zwischen Prädiktoren und AV

# Data
df_subscales<- df2_long %>% dplyr::select(EFT_all:PE_all)

# Plots (Visuelle Analyse der Linearität zwischen Prädiktoren und AV)
subscale_names <- colnames(df_subscales) 
plot_list = list() 
n = 0
for (i in subscale_names) {
  n <- n+1
  x <- c(str_glue("{i}*Time +","(Time|pat_id)"))
  form <- reformulate(x,response="Pomvalue")
  mx <- lmer(form, data = df2_long)
  mx_plot<-plot(resid(mx),df2$Pomvalue, main=i, ylab="Composite Score", xlab="Residuals")
}

3.2.2 Varianzhomogenität (homoscedasticity)

leveneTest(df2_long$Pomvalue, df2_long$Time)
## Levene's Test for Homogeneity of Variance (center = median)
##        Df F value  Pr(>F)  
## group   5  2.1993 0.05425 .
##       313                  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

3.2.3 Normalverteilung der Residuen

df2_long$zSR_all <- scale(df2_long$SR_all)
df2_long$zEFT_all <- scale(df2_long$EFT_all)
df2_long$zB_all <- scale(df2_long$B_all)
df2_long$zC_all <- scale(df2_long$C_all)
df2_long$zI_all <- scale(df2_long$I_all)
df2_long$zPC_all <- scale(df2_long$PC_all)
df2_long$zCF_all <- scale(df2_long$CF_all)
df2_long$zDB_all <- scale(df2_long$DB_all)
df2_long$zPD_all <- scale(df2_long$PD_all)
df2_long$zPE_all <- scale(df2_long$PE_all)

PlotQQ(df2_long$zSR_all)

PlotQQ(df2_long$zEFT_all)

PlotQQ(df2_long$zB_all)

PlotQQ(df2_long$zC_all)

PlotQQ(df2_long$zI_all)

PlotQQ(df2_long$zPC_all)

PlotQQ(df2_long$zCF_all)

PlotQQ(df2_long$zDB_all)

PlotQQ(df2_long$zPD_all)

PlotQQ(df2_long$zPE_all)

summary(Linear.model.test <- lm(Pomvalue ~ SR_all + EFT_all + B_all + I_all + C_all
                                + PC_all + CF_all + DB_all + PD_all, PE_all, data = df2_long))
## 
## Call:
## lm(formula = Pomvalue ~ SR_all + EFT_all + B_all + I_all + C_all + 
##     PC_all + CF_all + DB_all + PD_all, data = df2_long, subset = PE_all)
## 
## Residuals:
##        Min         1Q     Median         3Q        Max 
## -8.838e-12  1.400e-15  1.400e-15  5.290e-14  1.593e-13 
## 
## Coefficients: (7 not defined because of singularities)
##               Estimate Std. Error    t value Pr(>|t|)    
## (Intercept)  4.032e+01  1.186e-13  3.398e+14   <2e-16 ***
## SR_all       4.091e+01  1.725e-13  2.372e+14   <2e-16 ***
## EFT_all     -1.961e+01  1.289e-13 -1.521e+14   <2e-16 ***
## B_all               NA         NA         NA       NA    
## I_all               NA         NA         NA       NA    
## C_all               NA         NA         NA       NA    
## PC_all              NA         NA         NA       NA    
## CF_all              NA         NA         NA       NA    
## DB_all              NA         NA         NA       NA    
## PD_all              NA         NA         NA       NA    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4.659e-13 on 363 degrees of freedom
## Multiple R-squared:      1,  Adjusted R-squared:      1 
## F-statistic: 4.368e+28 on 2 and 363 DF,  p-value: < 2.2e-16
ols_test_normality(Linear.model.test)
## -----------------------------------------------
##        Test             Statistic       pvalue  
## -----------------------------------------------
## Shapiro-Wilk              0.047          0.0000 
## Kolmogorov-Smirnov        0.4945         0.0000 
## Cramer-von Mises           122           0.0000 
## Anderson-Darling         124.4669        0.0000 
## -----------------------------------------------
plot(Linear.model.test)

3.3 HLM Modelle

3.3.1 Intercept-Only Modell

intercept.only.model <- lmer(data = df2_long, Pomvalue ~ 1 + (1 | pat_id), REML = TRUE)

summary(intercept.only.model) 
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pomvalue ~ 1 + (1 | pat_id)
##    Data: df2_long
## 
## REML criterion at convergence: 3087.7
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.5843 -0.6905 -0.2231  0.5518  3.0178 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev.
##  pat_id   (Intercept) 313.9    17.72   
##  Residual             765.4    27.67   
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error     df t value Pr(>|t|)    
## (Intercept)   45.329      2.768 60.730   16.38   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
confint(intercept.only.model)
##                2.5 %   97.5 %
## .sig01      13.24199 22.68635
## .sigma      25.44700 30.22198
## (Intercept) 39.85829 50.78983
performance::r2(intercept.only.model) 
## # R2 for Mixed Models
## 
##   Conditional R2: 0.291
##      Marginal R2: 0.000
performance::icc(intercept.only.model)
## # Intraclass Correlation Coefficient
## 
##      Adjusted ICC: 0.291
##   Conditional ICC: 0.291
# Explained Variance verglichen mit dem "null-model"
ranova(intercept.only.model)
## ANOVA-like table for random-effects: Single term deletions
## 
## Model:
## Pomvalue ~ (1 | pat_id)
##              npar  logLik    AIC    LRT Df Pr(>Chisq)    
## <none>          3 -1543.9 3093.7                         
## (1 | pat_id)    2 -1564.8 3133.7 41.928  1  9.468e-11 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

3.3.2 Time-as-Only-Predictor Modell

time.only.model <- lmer(data = df2_long, Pomvalue ~ Time + (1 | pat_id), REML = TRUE)

summary(time.only.model)
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pomvalue ~ Time + (1 | pat_id)
##    Data: df2_long
## 
## REML criterion at convergence: 2978.2
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0505 -0.5922 -0.1543  0.4917  3.6067 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev.
##  pat_id   (Intercept) 372.1    19.29   
##  Residual             503.6    22.44   
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error       df t value Pr(>|t|)    
## (Intercept)  65.3933     3.2839 111.9413   19.91   <2e-16 ***
## Time         -8.8135     0.7597 265.3743  -11.60   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##      (Intr)
## Time -0.528
confint(time.only.model)
##                 2.5 %    97.5 %
## .sig01       15.21743 24.039741
## .sigma       20.59938 24.476104
## (Intercept)  58.94238 71.840174
## Time        -10.30240 -7.318512
anova(intercept.only.model, time.only.model) # Explained Variance compared to intercept-only model
## Data: df2_long
## Models:
## intercept.only.model: Pomvalue ~ 1 + (1 | pat_id)
## time.only.model: Pomvalue ~ Time + (1 | pat_id)
##                      npar    AIC    BIC  logLik deviance  Chisq Df Pr(>Chisq)
## intercept.only.model    3 3097.6 3108.9 -1545.8   3091.6                     
## time.only.model         4 2991.3 3006.4 -1491.7   2983.3 108.28  1  < 2.2e-16
##                         
## intercept.only.model    
## time.only.model      ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
performance::r2(time.only.model) 
## # R2 for Mixed Models
## 
##   Conditional R2: 0.541
##      Marginal R2: 0.202
0.207/0.632 # f2 = Marginal intercept.only - marginal time.only/1 - 
## [1] 0.3275316
performance::icc(time.only.model)
## # Intraclass Correlation Coefficient
## 
##      Adjusted ICC: 0.425
##   Conditional ICC: 0.339

3.3.2.1 Time-as-Only-Predictor Modell: Random-Effects Modelle

time2.only.model <- lmer(data = df2_long, Pomvalue ~ Time + (Time | pat_id), REML = TRUE)
summary (time2.only.model)
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pomvalue ~ Time + (Time | pat_id)
##    Data: df2_long
## 
## REML criterion at convergence: 2964.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0600 -0.5311 -0.1367  0.3866  3.7634 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 653.3    25.559        
##           Time         26.2     5.119   -0.66
##  Residual             413.4    20.332        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)    
## (Intercept)  65.2064     3.8203 60.8709  17.068  < 2e-16 ***
## Time         -8.7489     0.9648 58.1973  -9.068 9.94e-13 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##      (Intr)
## Time -0.685
confint(time2.only.model)
##                   2.5 %     97.5 %
## .sig01       19.6782293 32.2240408
## .sig02       -0.8428782 -0.3444323
## .sig03        2.9960091  7.1163074
## .sigma       18.4884036 22.5031125
## (Intercept)  57.6463104 72.7366312
## Time        -10.6518008 -6.8370639
anova(time.only.model, time2.only.model)
## Data: df2_long
## Models:
## time.only.model: Pomvalue ~ Time + (1 | pat_id)
## time2.only.model: Pomvalue ~ Time + (Time | pat_id)
##                  npar    AIC    BIC  logLik deviance  Chisq Df Pr(>Chisq)   
## time.only.model     4 2991.3 3006.4 -1491.7   2983.3                        
## time2.only.model    6 2982.1 3004.7 -1485.0   2970.1 13.218  2   0.001348 **
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
performance::r2(time2.only.model) 
## # R2 for Mixed Models
## 
##   Conditional R2: 0.624
##      Marginal R2: 0.199
0.218 # 0.484
## [1] 0.218
1 - 0.702 # 0.298
## [1] 0.298
0.484/0.298# f2 = 0.31
## [1] 1.624161
performance::icc(time2.only.model) # adjusted --> ICC
## # Intraclass Correlation Coefficient
## 
##      Adjusted ICC: 0.531
##   Conditional ICC: 0.425
# Random Effects of Therapists
th.model <- lmer(data = df2_long, Pomvalue ~ 1 + (Time | the_id/pat_id), REML = TRUE)

3.3.3 Theorie-Spezifische Subskalen als Prädiktoren

df_subscales<- df2_long %>% dplyr::select(EFT_all:PE_all)
subscale_names <- colnames(df_subscales) 
plot_list = list() 
n = 0
for (i in subscale_names) {
  n <- n+1
  x <- c(str_glue("{i}*Time +","(Time|pat_id)"))
  form <- reformulate(x,response="Pomvalue")
  mx <- lmer(form, data = df2_long)
  print("______________________________________________") 
  print("Subskala:")
  print(i)
  print(summary(mx))
}
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "EFT_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2954.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0651 -0.5268 -0.1312  0.3805  3.7394 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 656.36   25.619        
##           Time         26.91    5.187   -0.66
##  Residual             413.39   20.332        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##              Estimate Std. Error     df t value Pr(>|t|)  
## (Intercept)    48.626     19.419 59.267   2.504    0.015 *
## EFT_all         7.889      9.055 59.237   0.871    0.387  
## Time           -6.451      5.015 58.072  -1.286    0.203  
## EFT_all:Time   -1.094      2.329 57.672  -0.470    0.640  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) EFT_ll Time  
## EFT_all     -0.980              
## Time        -0.679  0.665       
## EFT_all:Tim  0.668 -0.680 -0.981
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "SR_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2952
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0914 -0.5197 -0.1349  0.4054  3.7439 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 665.82   25.804        
##           Time         26.06    5.105   -0.67
##  Residual             413.13   20.326        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)   
## (Intercept)  64.8627    19.4816 58.9784   3.329   0.0015 **
## SR_all        0.2428    12.3412 58.9338   0.020   0.9844   
## Time         -3.6839     4.7890 54.8439  -0.769   0.4450   
## SR_all:Time  -3.2844     3.0402 55.3224  -1.080   0.2847   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) SR_all Time  
## SR_all      -0.980              
## Time        -0.694  0.681       
## SR_all:Time  0.680 -0.694 -0.980
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "DB_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2954.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0898 -0.5400 -0.1152  0.3828  3.7484 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 663.94   25.767        
##           Time         26.62    5.159   -0.66
##  Residual             413.59   20.337        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error     df t value Pr(>|t|)   
## (Intercept)   56.192     18.703 59.727   3.004  0.00388 **
## DB_all         4.824      9.806 59.555   0.492  0.62455   
## Time          -5.420      4.776 58.460  -1.135  0.26113   
## DB_all:Time   -1.774      2.490 58.191  -0.712  0.47914   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) DB_all Time  
## DB_all      -0.979              
## Time        -0.680  0.665       
## DB_all:Time  0.669 -0.683 -0.979
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "I_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2952.2
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0559 -0.5293 -0.1321  0.4020  3.7608 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 670.82   25.900        
##           Time         25.58    5.058   -0.70
##  Residual             413.89   20.344        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error     df t value Pr(>|t|)    
## (Intercept)   66.965     12.216 59.907   5.482 8.87e-07 ***
## I_all         -1.046      6.891 59.525  -0.152    0.880    
## Time          -4.773      3.011 58.438  -1.585    0.118    
## I_all:Time    -2.371      1.704 58.768  -1.392    0.169    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##            (Intr) I_all  Time  
## I_all      -0.949              
## Time       -0.712  0.676       
## I_all:Time  0.674 -0.711 -0.948
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "B_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2951.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0484 -0.5318 -0.1341  0.4229  3.7367 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 644.09   25.379        
##           Time         24.73    4.973   -0.64
##  Residual             413.40   20.332        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error     df t value Pr(>|t|)
## (Intercept)   31.793     28.113 59.215   1.131    0.263
## B_all         15.807     13.173 59.097   1.200    0.235
## Time           1.917      6.896 53.820   0.278    0.782
## B_all:Time    -5.046      3.229 53.823  -1.563    0.124
## 
## Correlation of Fixed Effects:
##            (Intr) B_all  Time  
## B_all      -0.991              
## Time       -0.679  0.673       
## B_all:Time  0.673 -0.680 -0.990
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "C_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2949.7
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0427 -0.5240 -0.1632  0.4328  3.6906 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 631.97   25.139        
##           Time         22.74    4.768   -0.63
##  Residual             412.25   20.304        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error     df t value Pr(>|t|)  
## (Intercept)   27.604     25.927 58.940   1.065   0.2914  
## C_all         16.201     11.050 58.897   1.466   0.1479  
## Time           5.132      6.196 52.569   0.828   0.4113  
## C_all:Time    -5.973      2.634 52.335  -2.268   0.0275 *
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##            (Intr) C_all  Time  
## C_all      -0.989              
## Time       -0.673  0.666       
## C_all:Time  0.667 -0.675 -0.989
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "PC_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2951.7
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0620 -0.5324 -0.0966  0.4283  3.7941 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 646.43   25.425        
##           Time         24.32    4.932   -0.64
##  Residual             411.02   20.274        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error     df t value Pr(>|t|)  
## (Intercept)   20.400     38.017 59.092   0.537   0.5935  
## PC_all        10.550      8.914 59.008   1.184   0.2413  
## Time           9.530      9.496 58.413   1.004   0.3197  
## PC_all:Time   -4.301      2.222 58.007  -1.935   0.0578 .
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) PC_all Time  
## PC_all      -0.995              
## Time        -0.672  0.668       
## PC_all:Time  0.670 -0.673 -0.995
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "PD_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2950.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0559 -0.5306 -0.1229  0.3799  3.7537 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 631.16   25.123        
##           Time         25.74    5.074   -0.64
##  Residual             412.94   20.321        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error     df t value Pr(>|t|)
## (Intercept)   30.345     21.838 59.788   1.390    0.170
## PD_all        25.292     15.602 59.784   1.621    0.110
## Time          -1.480      5.490 56.743  -0.270    0.788
## PD_all:Time   -5.274      3.917 56.688  -1.346    0.184
## 
## Correlation of Fixed Effects:
##             (Intr) PD_all Time  
## PD_all      -0.985              
## Time        -0.680  0.670       
## PD_all:Time  0.671 -0.680 -0.985
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "CF_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2953.1
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0507 -0.5310 -0.1336  0.3934  3.7476 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 665.89   25.805        
##           Time         27.26    5.221   -0.66
##  Residual             413.24   20.328        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error       df t value Pr(>|t|)
## (Intercept)  93.6225    68.9246  60.0119   1.358    0.179
## CF_all       -6.2142    15.0443  60.0325  -0.413    0.681
## Time        -10.3072    17.5708  58.0372  -0.587    0.560
## CF_all:Time   0.3425     3.8272  57.8985   0.089    0.929
## 
## Correlation of Fixed Effects:
##             (Intr) CF_all Time  
## CF_all      -0.998              
## Time        -0.684  0.683       
## CF_all:Time  0.684 -0.685 -0.998
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "PE_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df2_long
## 
## REML criterion at convergence: 2954.3
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0582 -0.5192 -0.1200  0.3934  3.7169 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 657.10   25.634        
##           Time         27.29    5.224   -0.66
##  Residual             412.62   20.313        
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)   
## (Intercept)  49.7500    18.5289 59.0771   2.685   0.0094 **
## PE_all        7.5234     8.8193 59.0955   0.853   0.3971   
## Time         -8.2171     4.7841 58.1874  -1.718   0.0912 . 
## PE_all:Time  -0.2643     2.2709 58.0848  -0.116   0.9077   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) PE_all Time  
## PE_all      -0.978              
## Time        -0.682  0.667       
## PE_all:Time  0.669 -0.683 -0.979

4 Zusätzliche Analysen

4.1 Emotion focused and anxiety symptomatology

4.1.1 Data

df3_long <- select(df2, BAI_t1, BAI_t2, BAI_t3, BAI_t4, BAI_t5, BAI_t6, 
                   BSI_t1, BSI_t2, BSI_t3, BSI_t4, BSI_t5, BSI_t6,
                   BDI_t1, BDI_t2, BDI_t3, BDI_t4, BDI_t5, BDI_t6,
                   n_sessions, age_th, age_pat_startth, pom_pre, pom_int1, pom_int2, pom_post, pom_fu1, pom_fu2, pat_id, the_id, pat_sex, the_sex, EFT_all, SR_all, DB_all, I_all, B_all, C_all, PC_all, PD_all, CF_all, PE_all)%>%
  gather("Time","BAIvalue", BAI_t1: BAI_t6 ) %>% 
  mutate(Time = replace(Time,Time=="BAI_t1", "0")) %>%
  mutate(Time = replace(Time,Time=="BAI_t2", "1")) %>%
  mutate(Time = replace(Time,Time=="BAI_t3", "2")) %>%
  mutate(Time = replace(Time,Time=="BAI_t4", "3")) %>%
  mutate(Time = replace(Time,Time=="BAI_t5", "4"))%>%
  mutate(Time = replace(Time,Time=="BAI_t6", "5"))%>%
  mutate(Time = as.numeric(Time))

4.1.2 Intercept-Only Modell

BAIintercept.only.model <- lmer(data = df3_long, BAIvalue ~ 1 + (1 | pat_id), REML = TRUE)
BAIintercept.only.model
## Linear mixed model fit by REML ['lmerModLmerTest']
## Formula: BAIvalue ~ 1 + (1 | pat_id)
##    Data: df3_long
## REML criterion at convergence: 2199.507
## Random effects:
##  Groups   Name        Std.Dev.
##  pat_id   (Intercept) 5.250   
##  Residual             6.656   
## Number of obs: 319, groups:  pat_id, 61
## Fixed Effects:
## (Intercept)  
##       9.652
summary(BAIintercept.only.model)
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: BAIvalue ~ 1 + (1 | pat_id)
##    Data: df3_long
## 
## REML criterion at convergence: 2199.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.8822 -0.6008 -0.1928  0.4537  4.1825 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev.
##  pat_id   (Intercept) 27.57    5.250   
##  Residual             44.30    6.656   
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error     df t value Pr(>|t|)    
## (Intercept)    9.652      0.774 59.086   12.47   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
confint(BAIintercept.only.model)
##                2.5 %    97.5 %
## .sig01      4.075937  6.596126
## .sigma      6.120554  7.274236
## (Intercept) 8.125465 11.182898
ranova(BAIintercept.only.model)
## ANOVA-like table for random-effects: Single term deletions
## 
## Model:
## BAIvalue ~ (1 | pat_id)
##              npar  logLik    AIC    LRT Df Pr(>Chisq)    
## <none>          3 -1099.8 2205.5                         
## (1 | pat_id)    2 -1132.2 2268.4 64.897  1  7.892e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
performance::r2(BAIintercept.only.model) 
## # R2 for Mixed Models
## 
##   Conditional R2: 0.384
##      Marginal R2: 0.000
performance::icc(BAIintercept.only.model)
## # Intraclass Correlation Coefficient
## 
##      Adjusted ICC: 0.384
##   Conditional ICC: 0.384

4.1.3 Time-as-Only-Predictor Modell

BAItime.only.model <- lmer(data = df3_long, BAIvalue ~ Time + (1 | pat_id), REML = TRUE)

summary(BAItime.only.model)
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: BAIvalue ~ Time + (1 | pat_id)
##    Data: df3_long
## 
## REML criterion at convergence: 2132.3
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.2556 -0.6016 -0.1954  0.4213  4.5469 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev.
##  pat_id   (Intercept) 28.49    5.337   
##  Residual             34.33    5.859   
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error       df t value Pr(>|t|)    
## (Intercept)  13.6506     0.8868 105.9200  15.393   <2e-16 ***
## Time         -1.7508     0.1985 264.1423  -8.822   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##      (Intr)
## Time -0.510
confint(BAItime.only.model)
##                 2.5 %    97.5 %
## .sig01       4.231574  6.631816
## .sigma       5.377369  6.391234
## (Intercept) 11.907528 15.391651
## Time        -2.140652 -1.361398
performance::r2(time.only.model) 
## # R2 for Mixed Models
## 
##   Conditional R2: 0.541
##      Marginal R2: 0.202
0.207/0.632 # f2 = Marginal intercept.only - marginal time.only/1 - 
## [1] 0.3275316
performance::icc(time.only.model)
## # Intraclass Correlation Coefficient
## 
##      Adjusted ICC: 0.425
##   Conditional ICC: 0.339
# Conditional R2: 0.633
# Marginal R2: 0.222

anova(BAIintercept.only.model, BAItime.only.model)
## Data: df3_long
## Models:
## BAIintercept.only.model: BAIvalue ~ 1 + (1 | pat_id)
## BAItime.only.model: BAIvalue ~ Time + (1 | pat_id)
##                         npar    AIC    BIC  logLik deviance  Chisq Df
## BAIintercept.only.model    3 2206.8 2218.1 -1100.4   2200.8          
## BAItime.only.model         4 2140.2 2155.2 -1066.1   2132.2 68.675  1
##                         Pr(>Chisq)    
## BAIintercept.only.model               
## BAItime.only.model       < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

4.1.3.1 Time-as-Only-Predictor Modell: Random-Effects Modelle

BAItime2.only.model <- lmer(data = df3_long, BAIvalue ~ Time + (Time | pat_id), REML = TRUE)
summary (BAItime2.only.model)
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: BAIvalue ~ Time + (Time | pat_id)
##    Data: df3_long
## 
## REML criterion at convergence: 2117.4
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0130 -0.5387 -0.1397  0.4304  4.5612 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 43.936   6.628         
##           Time         2.073   1.440    -0.57
##  Residual             27.442   5.239         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)    
## (Intercept)  13.6344     0.9894 60.1521  13.781  < 2e-16 ***
## Time         -1.7802     0.2609 55.1441  -6.822 7.29e-09 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##      (Intr)
## Time -0.632
anova(BAItime.only.model, BAItime2.only.model)
## Data: df3_long
## Models:
## BAItime.only.model: BAIvalue ~ Time + (1 | pat_id)
## BAItime2.only.model: BAIvalue ~ Time + (Time | pat_id)
##                     npar    AIC    BIC  logLik deviance  Chisq Df Pr(>Chisq)
## BAItime.only.model     4 2140.2 2155.2 -1066.1   2132.2                     
## BAItime2.only.model    6 2129.8 2152.4 -1058.9   2117.8 14.311  2  0.0007806
##                        
## BAItime.only.model     
## BAItime2.only.model ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
performance::r2(time2.only.model) 
## # R2 for Mixed Models
## 
##   Conditional R2: 0.624
##      Marginal R2: 0.199
0.218 # 0.484
## [1] 0.218
1 - 0.702 # 0.298
## [1] 0.298
0.484/0.298# f2 = 0.31
## [1] 1.624161
performance::icc(BAItime2.only.model) # adjusted --> ICC
## # Intraclass Correlation Coefficient
## 
##      Adjusted ICC: 0.566
##   Conditional ICC: 0.495
# Random Effects of Therapists
th.model <- lmer(data = df2_long, Pomvalue ~ 1 + (Time | the_id/pat_id), REML = TRUE)

4.1.4 Theorie-Spezifische Subskalen als Prädiktoren

for (i in subscale_names) {
    x <- c(str_glue("{i}*Time +","(Time|pat_id)"))
    form <- reformulate(x,response="BAIvalue")
    mx_BAI <- lmer(form, data = df3_long)
  print("______________________________________________") 
  print("Subskala:")
  print(i)
  print(summary(mx_BAI))
}
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "EFT_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2111.4
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0167 -0.5311 -0.1384  0.4187  4.5499 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 42.928   6.552         
##           Time         2.103   1.450    -0.56
##  Residual             27.449   5.239         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##              Estimate Std. Error      df t value Pr(>|t|)
## (Intercept)    6.6607     4.9784 58.7315   1.338    0.186
## EFT_all        3.3179     2.3213 58.6917   1.429    0.158
## Time          -0.8146     1.3533 55.3726  -0.602    0.550
## EFT_all:Time  -0.4593     0.6284 54.9545  -0.731    0.468
## 
## Correlation of Fixed Effects:
##             (Intr) EFT_ll Time  
## EFT_all     -0.980              
## Time        -0.625  0.612       
## EFT_all:Tim  0.615 -0.626 -0.981
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "SR_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2110.7
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.9377 -0.5346 -0.1479  0.4134  4.5611 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 44.515   6.672         
##           Time         2.081   1.443    -0.56
##  Residual             27.353   5.230         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)  
## (Intercept)  10.5466     5.0320 58.2509   2.096   0.0404 *
## SR_all        1.9997     3.1877 58.2117   0.627   0.5329  
## Time         -0.1939     1.2968 52.3402  -0.149   0.8817  
## SR_all:Time  -1.0280     0.8230 52.7931  -1.249   0.2171  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) SR_all Time  
## SR_all      -0.980              
## Time        -0.631  0.619       
## SR_all:Time  0.618 -0.631 -0.980
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "DB_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2110
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.9788 -0.5443 -0.1398  0.4123  4.5229 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 41.725   6.460         
##           Time         2.014   1.419    -0.54
##  Residual             27.429   5.237         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error       df t value Pr(>|t|)  
## (Intercept)  5.49411    4.72413 58.71606   1.163   0.2495  
## DB_all       4.36053    2.47668 58.53618   1.761   0.0835 .
## Time        -0.08675    1.27797 55.35224  -0.068   0.9461  
## DB_all:Time -0.90421    0.66563 55.06551  -1.358   0.1799  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) DB_all Time  
## DB_all      -0.979              
## Time        -0.613  0.599       
## DB_all:Time  0.603 -0.615 -0.979
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "I_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2111.7
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0075 -0.5595 -0.1110  0.4262  4.5333 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 44.562   6.675         
##           Time         2.006   1.416    -0.59
##  Residual             27.526   5.247         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)    
## (Intercept)  14.5050     3.1500 59.2951   4.605 2.23e-05 ***
## I_all        -0.5164     1.7770 58.9167  -0.291    0.772    
## Time         -0.9285     0.8114 53.9354  -1.144    0.258    
## I_all:Time   -0.5090     0.4590 54.2438  -1.109    0.272    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##            (Intr) I_all  Time  
## I_all      -0.949              
## Time       -0.650  0.617       
## I_all:Time  0.615 -0.649 -0.948
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "B_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2100.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.9218 -0.5273 -0.1415  0.3925  4.4884 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 34.86    5.904         
##           Time         1.61    1.269    -0.42
##  Residual             27.38    5.232         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)   
## (Intercept)  -8.6490     6.7317 57.7702  -1.285  0.20399   
## B_all        10.5399     3.1540 57.6432   3.342  0.00147 **
## Time          3.4653     1.7738 50.7393   1.954  0.05627 . 
## B_all:Time   -2.4782     0.8303 50.7567  -2.985  0.00436 **
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##            (Intr) B_all  Time  
## B_all      -0.991              
## Time       -0.564  0.559       
## B_all:Time  0.559 -0.565 -0.990
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "C_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2106.4
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.9114 -0.5336 -0.1376  0.3788  4.5221 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 39.983   6.323         
##           Time         1.763   1.328    -0.49
##  Residual             27.378   5.232         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)  
## (Intercept)  -0.4814     6.5652 57.9406  -0.073   0.9418  
## C_all         6.0807     2.7981 57.8953   2.173   0.0339 *
## Time          2.2237     1.6622 49.4007   1.338   0.1871  
## C_all:Time   -1.7209     0.7064 49.1857  -2.436   0.0185 *
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##            (Intr) C_all  Time  
## C_all      -0.989              
## Time       -0.594  0.587       
## C_all:Time  0.589 -0.595 -0.989
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "PC_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2112
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.9420 -0.5313 -0.1259  0.4227  4.6236 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 44.58    6.677         
##           Time         2.05    1.432    -0.57
##  Residual             27.43    5.238         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error       df t value Pr(>|t|)
## (Intercept) 13.82658    9.94556 58.43373   1.390    0.170
## PC_all      -0.04757    2.33201 58.34968  -0.020    0.984
## Time         0.70110    2.60553 54.67210   0.269    0.789
## PC_all:Time -0.58323    0.60985 54.30726  -0.956    0.343
## 
## Correlation of Fixed Effects:
##             (Intr) PC_all Time  
## PC_all      -0.995              
## Time        -0.633  0.630       
## PC_all:Time  0.631 -0.633 -0.995
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "PD_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2110.9
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0090 -0.5354 -0.1411  0.4392  4.5363 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 44.929   6.703         
##           Time         2.134   1.461    -0.57
##  Residual             27.424   5.237         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)  
## (Intercept)  12.8560     5.7748 58.9574   2.226   0.0298 *
## PD_all        0.5629     4.1257 58.9475   0.136   0.8919  
## Time         -0.9768     1.5001 53.5396  -0.651   0.5177  
## PD_all:Time  -0.5826     1.0702 53.4480  -0.544   0.5884  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) PD_all Time  
## PD_all      -0.985              
## Time        -0.638  0.628       
## PD_all:Time  0.629 -0.638 -0.985
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "CF_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2110.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0534 -0.5379 -0.1392  0.4152  4.6243 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 44.766   6.691         
##           Time         2.069   1.439    -0.57
##  Residual             27.429   5.237         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)
## (Intercept)  18.0880    17.8472 59.3131   1.013    0.315
## CF_all       -0.9721     3.8955 59.3303  -0.250    0.804
## Time         -6.0787     4.7025 55.0401  -1.293    0.202
## CF_all:Time   0.9370     1.0241 54.8949   0.915    0.364
## 
## Correlation of Fixed Effects:
##             (Intr) CF_all Time  
## CF_all      -0.998              
## Time        -0.629  0.628       
## CF_all:Time  0.629 -0.630 -0.998
## [1] "______________________________________________"
## [1] "Subskala:"
## [1] "PE_all"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: form
##    Data: df3_long
## 
## REML criterion at convergence: 2110.9
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0373 -0.5322 -0.1394  0.4433  4.5521 
## 
## Random effects:
##  Groups   Name        Variance Std.Dev. Corr 
##  pat_id   (Intercept) 42.918   6.551         
##           Time         2.139   1.462    -0.57
##  Residual             27.404   5.235         
## Number of obs: 319, groups:  pat_id, 61
## 
## Fixed effects:
##             Estimate Std. Error      df t value Pr(>|t|)
## (Intercept)   7.0658     4.7477 58.5261   1.488    0.142
## PE_all        3.1975     2.2597 58.5370   1.415    0.162
## Time         -1.4820     1.2920 55.4474  -1.147    0.256
## PE_all:Time  -0.1472     0.6131 55.3059  -0.240    0.811
## 
## Correlation of Fixed Effects:
##             (Intr) PE_all Time  
## PE_all      -0.978              
## Time        -0.632  0.618       
## PE_all:Time  0.620 -0.633 -0.979